浏览全部资源
扫码关注微信
Received：08 March 2018，
Accepted：06 June 2018，
Published：2019-03
移动端阅览
以北方典型河口湿地—黄河三角洲湿地为研究区，采用在特征选择和分类提取等方面具有明显优势的随机森林算法，对研究区内的湿地信息进行提取。首先基于多时相、光谱信息丰富的Sentinel-2数据生成4类不同的特征变量，包括光谱特征、植被指数和水体指数、红边指数、纹理特征；再根据以上特征构建6种不同的提取方案，对黄河三角洲湿地信息进行提取并验证不同方案的提取精度，旨在选择最佳方案改善湿地信息提取的效果。结果表明：(1)有效地使用多种特征变量是提高湿地信息提取的关键，就不同特征对湿地信息提取的贡献率而言，红边指数>植被指数和水体指数>光谱特征>纹理特征；(2)基于随机森林算法优选的特征变量提取效果最佳，总体精度高达90.93%，Kappa系数为0.90，表明随机森林算法可以有效地进行特征选择，在特征变量数据挖掘的同时，仍能保证湿地信息提取的精度，提高运行效率。本研究为湿地信息提取在数据源选择、特征选择和方法选择方面提供了一种新思路、方法和技术手段。
Estuary wetland is a special wetland type
and the extraction of estuary wetland information plays an important role in wetland conservation and scientific research. In this study
Yellow River Delta wetlands
as a typical estuary wetland in the north part of China
are considered the study area. The random forest method
which has evident advantages in feature selection and classification
was chosen to extract wetland information from the study area. First
five different characteristic variables
namely
spectral features
vegetation index
water index
red edge index
and texture features
were generated based on Sentinel-2 data with rich multi-temporal and spectral information. Then
six different classification schemes were constructed based on the preceding characteristic information. Finally
random forest classifier was used to extract the wetland information of the Yellow River Delta and verify the extraction accuracy of different results. The purpose is to select the best plan to improve the effect of wetland information extraction. Results are as follows: (1) The effective use of multiple feature variables is the key to improving the extraction of wetland information. The contribution of different characteristics to the wetland information extraction is described as follows: the red edge index > vegetation index and water index > spectral feature > texture feature. (2) The preferred features based on the random forest algorithm are crucial to extraction accuracy
with an overall accuracy of up to 90.93%
and Kappa coefficient of 0.90. This result shows that the random forest algorithm can effectively process feature selection. In feature variable data mining
the accuracy of the wetland information extraction can be guaranteed
and the operation efficiency can be improved. This study also provides a new idea
method
and technology for the selection of data sources and feature and method selections for wetland information extraction.
Abuelgasim A A, Gopal S, Irons J R and Strahler A H. 1996. Classification of ASAS multiangle and multispectral measurements using artificial neural networks. Remote Sensing of Environment, 57(2): 79–87
Baker C, Lawrence R, Montagne C and Patten D. 2006. Mapping wetlands and riparian areas using Landsat ETM+ imagery and decision-tree-based models. Wetlands, 26(2): 465–474
Bao Y H and Ren J B. 2011. Wetland landscape classification based on the BP neural network in DaLinor Lake area. Procedia Environmental Sciences, 10: 2360–2366
Barnes E M, Clarke T R, Richards S E, Colaizzi P D, Haberland J, Kostrzewski M, Waller P, Choi C, Riley E, Thompson T, Lascano R J, Li H and Moran M S. 2000. Coincident detection of crop water stress, nitrogen status and canopy density using ground-based multispectral data//Proceedings of the 5th International Conference on Precision Agriculture. South Segoe Road, Madison: American Society of Agronomy.
Breiman L. 2001. Random forest. Machine Learning, 45(1): 5–32
Davranche A, Lefebvre G and Poulin B. 2010. Wetland monitoring using classification trees and SPOT-5 seasonal time series. Remote Sensing of Environment, 114(3): 552–562
Delegido J, Verrelst J, Alonso L and Moreno J. 2011. Evaluation of sentinel-2 red-edge bands for empirical estimation of green LAI and chlorophyll content. Sensors, 11(7): 7063–7081
Drusch M, Del Bello U, Carlier S, Colin O, Fernandez V, Gascon F, Hoersch B, Isola C, Laberinti P, Martimort P, Meygret A, Spoto F, Sy O, Marchese F and Bargellini P. 2012. Sentinel-2: ESA’s optical high-resolution mission for GMES operational services. Remote Sensing of Environment, 120: 25–36
Fernández-Manso A, Fernández-Manso O and Quintano C. 2016. SENTINEL-2A red-edge spectral indices suitability for discriminating burn severity. International Journal of Applied Earth Observation and Geoinformation, 50: 170–175
Genuer R, Poggi J M and Tuleau-Malot C. 2010. Variable selection using random forests. Pattern Recognition Letters, 31(14): 2225–2236
Gitelson A A, Gritz Y and Merzlyak M N. 2003. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. Journal of Plant Physiology, 160(3): 271–282
Gitelson A and Merzlyak M N. 1994. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation. Journal of Plant Physiology, 143(3): 286–292
宫宁, 牛振国, 齐伟, 张海英. 2016. 中国湿地变化的驱动力分析. 遥感学报, 20(2): 172–183
Gong N, Niu Z G, Qi W and Zhaug H Y. 2016. Driving forces of wetland change in China. Journal of Remote Sensing, 20(2): 172–183 (
Hill M J. 2013. Vegetation index suites as indicators of vegetation state in grassland and savanna: an analysis with simulated SENTINEL 2 data for a North American transect. Remote Sensing of Environment, 137: 94–111
侯群群, 王飞, 严丽. 2013. 基于灰度共生矩阵的彩色遥感图像纹理特征提取. 国土资源遥感, 25(4): 26–32
Hou Q Q, Wang F and Yan L. 2013. Extraction of color image texture feature based on gray-level co-occurrence matrix. Remote Sensing for Land and Resources, 25(4): 26–32 (
胡玉福, 邓良基, 匡先辉, 王鹏, 何莎, 熊玲. 2011. 基于纹理特征的高分辨率遥感图像土地利用分类研究. 地理与地理信息科学, 27(5): 42–45, 68
Hu Y F, Deng J J, Kuang X H, Wang P, He S and Xiong L. 2011. Study on land use classification of high resolution remote sensing image based on texture feature. Geography and Geo-Information Science, 27(5): 42–45, 68 (
黄进良. 1999. 洞庭湖湿地的面积变化与演替. 地理研究, 18(3): 297–304
Huang J L. 1999. The area change and succession of Dongtinghu wetland. Geographical Research, 18(3): 297–304 (
黄葵, 石达扎实, 邓春蕾, 杜凯. 2012. 黄河口近海生态系统与入海径流的响应关系. 人民黄河, 34(11): 66–69
Huang K, Shida Z S, Deng C L and Du K. 2012. Response Relationship Between Ecosystem and Runoff into the Sea in the Yellow River Estuary. Yellow River, 34(11): 66–69 (
Iverson L R, Prasad A M, Matthews S N and Peters M. 2008. Estimating potential habitat for 134 eastern US tree species under six climate scenarios. Forest Ecology and Management, 254(3): 390–406
Khatami R, Mountrakis G and Stehman S V. 2016. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: general guidelines for practitioners and future research. Remote Sensing of Environment, 177: 89–100
Korhonen L, Hadi, Packalen P and Rautiainen M. 2017. Comparison of Sentinel-2 and Landsat 8 in the estimation of boreal forest canopy cover and leaf area index. Remote Sensing of Environment, 195: 259–274
刘红玉, 吕宪国, 张世奎. 2004. 三江平原流域湿地景观多样性及其50年变化研究. 生态学报, 24(7): 1472–1479
Liu H Y, Lv X G and Zhang S K. 2004. Landscape biodiversity of wetlands and their changes in 50 years in watersheds of the Sanjiang Plain. Acta Ecologica Sinica, 24(7): 1472–1479 (
刘莉, 韩美, 刘玉斌, 潘彬. 2017. 黄河三角洲自然保护区湿地植被生物量空间分布及其影响因素. 生态学报, 37(13): 4346–4355
Liu L, Han M, Liu Y B and Pan B. 2017. Spatial distribution of wetland vegetation biomass and its influencing factors in the Yellow River Delta Nature Reserve. Acta Ecologica Sinica, 37(13): 4346–4355 (
刘萌萌, 刘亚岚, 孙国庆, 彭立. 2014. 结合纹理特征的SVM样本分层土地覆盖分类. 遥感技术与应用, 29(2): 315–323
Liu M M, Liu Y L, Sun G Q and Peng L. 2014. SVM land cover classification based on spectral and textural features using stratified samples. Remote Sensing Technology and Application, 29(2): 315–323 (
刘润红, 梁士楚, 赵红艳, 漆光超, 李丽香, 姜勇, 牛振国. 2017. 中国滨海湿地遥感研究进展. 遥感技术与应用, 32(6): 998–1011
Liu R H, Liang S C, Zhao H Y, Qi G C, Li L X, Jiang Y and Niu Z G. 2017. Progress of Chinese coastal wetland based on remote sensing. Remote Sensing Technology and Application, 32(6): 998–1011 (
刘舒, 姜琦刚, 马玥, 肖艳, 李远华, 崔璨. 2017. 基于多目标遗传随机森林特征选择的面向对象湿地分类. 农业机械学报, 48(1): 119–127
Liu S, Jiang Q G, Ma Y, Xiao Y, Li Y H and Cui C. 2017. Object-oriented wetland classification based on hybrid feature selection method combining with relief F, multi-objective genetic algorithm and random forest. Transactions of the Chinese Society for Agricultural Machinery, 48(1): 119–127 (
牟晓杰, 刘兴土, 阎百兴, 崔保山. 2015. 中国滨海湿地分类系统. 湿地科学, 13(1): 19–26
Mou X J, Liu X T, Yan B X and Cui B S. 2015. Classification system of coastal wetlands in China. Wetland Science, 13(1): 19–26 (
那晓东, 张树清, 孔博, 于欢, 李晓峰, 刘春悦. 2008. 基于决策树方法的淡水沼泽湿地信息提取——以三江平原东北部为例. 遥感技术与应用, 23(4): 365–372
Na X D, Zhang S Q, Kong B, Yu H, Li X F and Liu C Y. 2008. The extraction of freshwater marsh wetland information based on decision tree algorithm——A case study in the Northeast of the Sanjiang Plain. Remote Sensing Technology and Application, 23(4): 365–372 (
Na X D, Zhang S Q, Zhang H Q, Li X F, Yu H and Liu C Y. 2009. Integrating TM and ancillary geographical data with classification trees for land cover classification of marsh area. Chinese Geographical Science, 19(2): 177–185
Özesmi S L. 2000. Satellite Remote Sensing of Wetlands and a Comparison of Classification Techniques. Twin Cities, MN: University of Minnesota
Pu R L and Landry S. 2012. A comparative analysis of high spatial resolution IKONOS and WorldView-2 imagery for mapping urban tree species. Remote Sensing of Environment, 124: 516–533
Shang J L, Liu J G, Ma B L, Zhao T, Jiao X F, Geng X Y, Huffman T, Kovacs J M and Walters D. 2015. Mapping spatial variability of crop growth conditions using RapidEye data in Northern Ontario, Canada. Remote Sensing of Environment, 168: 113–125
Shoko C and Mutanga O. 2017. Examining the strength of the newly-launched Sentinel 2 MSI sensor in detecting and discriminating subtle differences between C3 and C4 grass species. ISPRS Journal of Photogrammetry and Remote Sensing, 129: 32–40
宋红丽. 2015. 围填海活动对黄河三角洲滨海湿地生态系统类型变化和碳汇功能的影响. 长春: 中国科学院研究生院(东北地理与农业生态研究所)
Song H L. 2015. Influence of reclamation activities on ecosystem type and carbon sink function of the coastal wetland in the Yellow River estuary. Changchun: Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences.
苏伟, 张明政, 蒋坤萍, 朱德海, 黄健熙, 王鹏新. 2018. Sentinel-2卫星影像的大气校正方法. 光学学报, 38(1): 128001
Su W, Zhang M Z, Jiang K P, Zhu D H, Huang J X and Wang P X. 2018. Atmospheric correction method for sentinel-2 satellite imagery. Acta Optica Sinica, 38(1): 128001 (
Wang L, Dronova I, Gong P, Yang W B, Li Y R and Liu Q. 2012. A new time series vegetation–water index of phenological–hydrological trait across species and functional types for Poyang Lake wetland ecosystem. Remote Sensing of Environment, 125: 49–63
王雪宏, 栗云召, 孟焕, 董红芳, 郭岳, 佟守正. 2015. 黄河三角洲新生湿地植物群落分布格局. 地理科学, 35(8): 1021–1026
Wang X H, Li Y Z, Meng H, Dong H F, Guo Y and Tong S Z. 2015. Distribution pattern of plant community in new-born coastal wetland in the Yellow River Delta. Scientia Geographica Sinica, 35(8): 1021–1026 (
温庆可, 张增祥, 徐进勇, 左丽君, 汪潇, 刘斌, 赵晓丽, 易玲. 2011. 环渤海滨海湿地时空格局变化遥感监测与分析. 遥感学报, 15(1): 183–200
Wen Q K, Zhang Z X, Xu J Y, Zuo L J, Wang X, Liu B, Zhao X L and Yi L. 2011. Spatial and temporal change of wetlands in Bohai rim during 2000-2008: An analysis based on satellite images. Journal of Remote Sensing, 15(1): 183–200 (
武吉华, 张绅, 江源, 康慕谊, 邱扬. 2004. 植物地理学. 4版. 北京: 高等教育出版社
Wu J H, Zhang S, Jiang Y, Kang M Y and Qiu Y. 2004. Plant Geography. 4th ed. Beijing: Higher Education Press
肖锦成, 欧维新, 符海月. 2013. 基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆被分类. 生态学报, 33(23): 7496–7504
Xiao J C, Ou W X and Fu H Y. 2013. Land cover classification of Yancheng Coastal Natural Wetlands based on BP neural network and ETM+ remote sensing data. Acta Ecologica Sinica, 33(23): 7496–7504 (
张策, 臧淑英, 金竺, 张玉红. 2011. 基于支持向量机的扎龙湿地遥感分类研究. 湿地科学, 9(3): 263–269
Zhang C, Zang S Y, Jin Z and Zhang Y H. 2011. Remote sensing classification for Zhalong Wetlands based on support vector machine. Wetland Science, 9(3): 263–269 (
张猛, 曾永年, 朱永森. 2017. 面向对象方法的时间序列MODIS数据湿地信息提取——以洞庭湖流域为例. 遥感学报, 21(3): 479–492
Zhang M, Zeng Y N and Zhu Y S. 2017. Wetland mapping of Donting Lake Basin based on time-series MODIS data and object-oriented method. Journal of Remote Sensing, 21(3): 479–492 (
张树文, 颜凤芹, 于灵雪, 卜坤, 杨久春, 常丽萍. 2013. 湿地遥感研究进展. 地理科学, 33(11): 1406–1412
Zhang S W, Yan F Q, Yu L X, Bu K, Yang J C and Chang L P. 2013. Application of remote sensing technology to wetland research. Scientia Geographica Sinica, 33(11): 1406–1412 (
张绪良, 叶思源, 印萍, 陈东景. 2009. 黄河三角洲自然湿地植被的特征及演化. 生态环境学报, 18(1): 292–298
Zhang X L, Ye S Y, Yin P and Chen D J. 2009. Characters and successions of natural wetland vegetation in Yellow River Delta. Ecology and Environmental Sciences, 18(1): 292–298 (
郑淑丹, 郑江华, 石明辉, 郭宝林, 森巴提, 孙志群, 贾晓光, 李晓瑾. 2014. 基于分形和灰度共生矩阵纹理特征的种植型药用植物遥感分类. 遥感学报, 18(4): 868–886
Zheng S D, Zheng J H, Shi M H, Guo B L, Sen B T, Sun Z Q, Jia X G and Li X J. 2014. Classification of cultivated Chinese medicinal plants based on fractal theory and gray level co-occurrence matrix textures. Journal of Remote Sensing, 18(4): 868–886 (
郑阳, 吴炳方, 张淼. 2017. Sentinel-2数据的冬小麦地上干生物量估算及评价. 遥感学报, 21(2): 318–328
Zheng Y, Wu B F and Zhang M. 2017. Estimating the above ground biomass of winter wheat using the Sentinel-2 data. Journal of Remote Sensing, 21(2): 318–328 (
相关文章
相关作者
相关机构
京公网安备11010802024621